Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well beyond annotations: link expiry of ten minutes, single-person scope, that the tool itself holds no Google access and connects nothing, what Tommo does with the mail (reads 30 days, sends as them), and the calendar side-effect for admin/owner unless unticked. Annotations only cover read-only/idempotent safety; this text explains the actual behavior and side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Dense but front-loaded with the core answer (the link and what opening it does); subsequent sentences add necessary caveats. Slightly long for a single-purpose field, but each sentence carries non-redundant information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Complete for a zero-parameter link-getter: it states scope, duration, side effects, and the alternative tool, and there is no output schema to describe. Nothing an agent needs in order to call it or to route correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Zero parameters, so baseline is 4. The description correctly indicates no input is needed and clarifies that the identity comes from the signed-in session, which is useful context for a parameterless tool.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('the link ... to connect their own mailbox') and distinguishes from siblings by naming add_a_mailbox as the alternative for delegated Workspace accounts, as well as distinguishing from link_to_connect_a_calendar and link_to_connect_a_tommos_google_account by scope ('their own mailbox', 'that person only').

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explains the situation (signed-in person connecting their own mailbox by Google sign-in) and names an alternative path via add_a_mailbox for domain-wide delegation. It does not give explicit when-not-to-use guidance or a step-by-step flow, but the routing signal is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.